Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    The neuron responds to words that appear in formal legal procedural descriptions—especially past‐tense verbs and terms (like “was,” “case,” “instituted,” “scheduled,” “directed,” etc.) recounting the history or status of a court action.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ější
    -0.07
     الغ
    -0.07
     sculptures
    -0.07
     pear
    -0.07
    Pizza
    -0.07
     cafe
    -0.07
     scarf
    -0.06
     payment
    -0.06
     Observatory
    -0.06
    .Use
    -0.06
    POSITIVE LOGITS
     singled
    0.07
     المخت
    0.06
    ทำงาน
    0.06
    未
    0.06
    ْ
    0.06
    <TreeNode
    0.06
    �
    0.06
    ặt
    0.06
    重新
    0.06
    선
    0.06
    Act Density 0.012%

    No Known Activations